CD product-analytics-setup
How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.
How to actually instrument product analytics correctly.
As a process D 48/100 · Unfinished process — References files that are not bundled: references/retention-measurement-patterns.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5652 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/retention-measurement-patterns.md - note
frontmatter-keyunknown frontmatter key "catalog_summary" - note
frontmatter-keyunknown frontmatter key "display_order" - note
edit-residuethe text marks something as outdated (lines 216, 273): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 48/100
- 0Tools and files. 1 referenced file(s) missing: references/retention-measurement-patterns.md
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5652 tokens
- 100Steps. 101 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 821: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 101 items
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.